feat(medsam): set min_area=100 with max_regions=20 for more fine segments

app.py

@@ -668,7 +668,7 @@ def analyze_with_medsam(base_result, image, include_raw_masks=False):
         masks_for_overlay = []
 
         # MedSAM over candidate boxes (original behavior)
-        cand_bboxes = _find_topk_foreground_bboxes(pil_img, max_regions=8, min_area=200)
+        cand_bboxes = _find_topk_foreground_bboxes(pil_img, max_regions=20, min_area=100)
         log(f"analyze_with_medsam: candidate boxes={len(cand_bboxes)}")
         for bbox in cand_bboxes:
             m = _medsam.segment_with_box(bbox)